© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 39629
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_57_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    henderit
    0.43
     ނ
    0.39
     भाऊ
    0.38
     Nec
    0.38
     Eph
    0.37
    ɖ
    0.37
    Readable
    0.37
    庁
    0.37
    uttosto
    0.36
     piuttosto
    0.36
    POSITIVE LOGITS
     sunken
    0.38
     scaffold
    0.38
     hear
    0.37
     вяза
    0.36
    raft
    0.35
     scarcity
    0.35
    成
    0.34
     영상
    0.34
     চালান
    0.33
     basal
    0.33
    Activations Density 0.000%

    No Known Activations